calibre/recipes/slate.recipe
2021-02-14 20:48:03 +05:30

86 lines
2.8 KiB
Python

#!/usr/bin/env python
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
__license__ = 'GPL v3'
'''
calibre recipe for slate.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class Slate(BasicNewsRecipe):
title = 'Slate'
description = 'A general-interest publication offering analysis and commentary about politics, news and culture.'
__author__ = 'Kovid Goyal'
timefmt = ''
no_stylesheets = True
language = 'en'
encoding = 'utf-8'
remove_attributes = ['style']
INDEX = 'https://slate.com'
compress_news_images = True
keep_only_tags = [
classes('article__header article__content'),
]
remove_tags = [
classes('social-share slate-ad newsletter-signup in-article-recirc'),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-srcset'].split()[0]
return soup
def parse_index(self):
ans = []
for sectitle, url in (
('News & Politics', '/articles/news_and_politics.html'),
('Technology', '/articles/technology.html'),
('Business', '/articles/business.html'),
('Arts', '/articles/arts.html'),
('Life', '/articles/life.html'),
('Health & Science', '/articles/health_and_science.html'),
('Sports', '/articles/sports.html'),
('Double X', '/articles/double_x.html'),
):
url = self.INDEX + url
self.log('\nFound section:', sectitle, url)
articles = self.slate_section_articles(self.index_to_soup(url))
if articles:
ans.append((sectitle, articles))
if self.test and len(ans) > 1:
break
return ans
def slate_section_articles(self, soup):
ans = []
main = soup.find('section', **classes('main'))
if main is None:
return ans
for div in main.findAll(**classes('section-feed__item')):
a = div.find('a')
url = a['href']
if url.endswith('/'):
continue
h = a.find(['h2', 'h3', 'h4'])
title = self.tag_to_string(h)
desc = ''
for q in ('byline', 'dek'):
span = div.find(attrs={'class': lambda x: x and ('-' + q) in x})
if span is not None:
desc += self.tag_to_string(span).strip()
self.log('\t' + title)
self.log('\t\t' + url)
ans.append({'title': title, 'description': desc.strip(),
'date': '', 'url': url})
return ans